Commit Graph

2113 Commits

Author SHA1 Message Date
Aliaksandr Valialkin
ebbef20535 lib/mergeset: use sort.IsSorted instead of sort.SliceIsSorted in inmemoryBlock.isSorted in order to reduce memory allocations 2019-09-19 20:13:54 +03:00
Aliaksandr Valialkin
89234f395d lib/storage: use sort.Sort instead of sort.slice in getSortedMetricIDs 2019-09-19 20:08:13 +03:00
Aliaksandr Valialkin
6e586fa09c lib/storage: skip duplicate call to intersectMetricIDsWithTagFilter on zero successful intersects 2019-09-19 17:51:10 +03:00
Aliaksandr Valialkin
410f993bf6 lib/mergeset: fill partHeader.firstItem on first block flush 2019-09-19 17:48:22 +03:00
Aliaksandr Valialkin
c05885fb5f lib/storage: mark tag filter returning errFallbackToMetricNameMatch as useless
This will save CPU on subsequent calls for this filter
2019-09-18 19:11:44 +03:00
Aliaksandr Valialkin
db71c940ea lib/storage: properly construct keys for uselessTagFiltersCache and register useless negative tag filters there 2019-09-17 23:18:37 +03:00
Aliaksandr Valialkin
41ef6b060e lib/mergeset: properly check for sorted block headers
Fix a typo for https://github.com/VictoriaMetrics/VictoriaMetrics/issues/181
2019-09-13 21:59:38 +03:00
hanzai
08cde5e3f4 lib/workingsetcache: adjust switching from mode=split to mode=whole smoothly and load cachefile successfully 2019-09-13 19:13:16 +03:00
Aliaksandr Valialkin
b101064f8b all: report the number of bytes read on io.ReadFull error
This should simplify error investigation similar to https://github.com/VictoriaMetrics/VictoriaMetrics/issues/175
2019-09-11 14:50:24 +03:00
Aliaksandr Valialkin
568ff61dcf lib/mergeset: dynamically calculate the maximum number of items per part, which can be cached in OS page cache 2019-09-09 11:42:45 +03:00
Aliaksandr Valialkin
2c654258ef lib/fs: add MustStopDirRemover for waiting until pending directories are removed on graceful shutdown
This patch is mainly required for laggy NFS. See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/162
2019-09-05 11:17:17 +03:00
Aliaksandr Valialkin
2c2bd897dd lib/storage: remove duplicate tag keys on MetricName.Marshal call
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/172
2019-09-04 18:13:51 +03:00
Aliaksandr Valialkin
82bfe818d0 lib/fs: try harder with directory removal on NFS in the event of temporary lock
Do not give up after 11 attempts of directory removal on laggy NFS.

Add `vm_nfs_dir_remove_failed_attempts_total` metric for counting the number of failed attempts
on directory removal.

Log failed attempts on directory removal after long sleep times.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/162
2019-09-04 12:24:41 +03:00
Aliaksandr Valialkin
0b0153ba3d lib/storage: invalidate tagFilters -> TSIDS cache when newly added index data becomes visible to search
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/163
2019-08-29 15:08:44 +03:00
Aliaksandr Valialkin
8504a38214 lib/prombp: apply ba06b47c16
The following commands used:

gofmt -r '(uint64(x)&0x7F)<<shift -> uint64(x&0x7F)<<shift' -w ./lib/prompb/
gofmt -r '(int64(x)&0x7F)<<shift -> int64(x&0x7F)<<shift' -w ./lib/prompb/
2019-08-29 13:35:54 +03:00
Aliaksandr Valialkin
604a4312f9 all: port to FreeBSD on GOARCH=amd64 2019-08-28 01:46:09 +03:00
Aliaksandr Valialkin
da07a6fb38 lib/storage: go fmt 2019-08-27 14:28:24 +03:00
Aliaksandr Valialkin
a63b69e9e2 lib/storage: report proper maxMetrics limit when more than -search.maxUniqueTimeseries series match the given filters 2019-08-27 14:21:31 +03:00
Aliaksandr Valialkin
82e813bad3 lib/storage: properly handle (?i) in the tag filter regexp
Fixes https://github.com/VictoriaMetrics/VictoriaMetrics/issues/161
2019-08-26 00:44:56 +03:00
Aliaksandr Valialkin
e2eac858b5 lib/storage: calculate the maximum number of rows per small part from -memory.allowedPercent
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/159

This simplifies error detection additionally to the `vm_rows_ignored_total` counters.
2019-08-25 15:29:09 +03:00
Aliaksandr Valialkin
0a8dd9cc9a lib/storage: calculate the maximum number of rows per small part from -memory.allowedPercent
This should improve query speed over recent data on machines with big amounts of RAM
2019-08-25 14:41:32 +03:00
Aliaksandr Valialkin
bc576fb386 lib/storage: properly limit the number of output rows in small and big parts storage
Previously small parts storage didn't take into account the available disk space for big parts.
2019-08-25 14:41:32 +03:00
Aliaksandr Valialkin
947decb3dd lib/storage: remove outdated comment on maxRowsPerSmallPart
The commend became outdated after the commit ed6ac1a5df027f0dfc22448e3b27c26b6f77c67a,
which stops merging of small parts on graceful shutdown instead of waiting
for their completion.
2019-08-25 13:46:10 +03:00
Aliaksandr Valialkin
c197641978 all: return 503 http error if service is temporarily unavailable
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/156
2019-08-23 09:49:50 +03:00
Aliaksandr Valialkin
e734076f0f app/vminsert: allow setting the maximum number of labels per time series via -maxLabelsPerTimeseries 2019-08-23 08:47:18 +03:00
Aliaksandr Valialkin
4ed63d033a lib/storage: add benchmarks for regexp filter match / mismatch
These benchmarks allow estimate the performance of regexp filters in promql
2019-08-22 16:37:19 +03:00
Aliaksandr Valialkin
6ec6a8d7c1 lib/storage: try slower path for searching the tag filter with the minimum number of matching time series before giving up with increase -search.maxUniqueTimeseries error 2019-08-19 16:07:05 +03:00
Aliaksandr Valialkin
c59f5c4865 lib/storage: pre-allocate memory for blockHeader slice in unmarshalBlockHeaders
This reduces memory usage and memory fragmentation when working with big number of time series
2019-08-19 12:46:45 +03:00
Aliaksandr Valialkin
f696cc503a lib/workingsetcache: automatically detect when it is better to double cache capacity 2019-08-15 22:58:04 +03:00
Aliaksandr Valialkin
99eed2ca14 lib/storage: properly cache tagFilters -> TSIDs entries from historical index 2019-08-14 02:32:25 +03:00
Aliaksandr Valialkin
f1d81b9405 lib/storage: compress contents of cache for tagFilters -> TSIDs
This should increase cache capacity
2019-08-14 02:32:22 +03:00
Aliaksandr Valialkin
8c2158af24 all: use workingsetcache instead of fastcache
This should reduce the amount of RAM required for processing time series
with non-zero churn rate.

The previous cache behavior can be restored with `-cache.oldBehavior` command-line flag.
2019-08-13 21:40:28 +03:00
Aliaksandr Valialkin
51263b1a45 lib/fs: add test for IsTemporaryFileName 2019-08-13 21:33:54 +03:00
Aliaksandr Valialkin
5a7ab0d90b lib/storage: remove broken BenchmarkIndexDBSearchTSIDs 2019-08-13 20:21:23 +03:00
Aliaksandr Valialkin
39f3f3a517 lib: move common code for creating flock.lock file into fs.CreateFlockFile 2019-08-13 01:46:20 +03:00
Aliaksandr Valialkin
73f866d874 lib/fs: atomically create file with the given contents on WriteFileAtomically
This should prevent from `transaction` and `metadata.json` files corruption
on unclean shutdown such as OOM, `kill -9`, power loss, etc.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/148
2019-08-12 15:02:04 +03:00
Aliaksandr Valialkin
4fb635b0c9 lib/storage: do not change timestamps to constant rate if values are constant or have constant delta
This breaks the original timestamps, which results in issues like
https://github.com/VictoriaMetrics/VictoriaMetrics/issues/120 and
https://github.com/VictoriaMetrics/VictoriaMetrics/issues/141 .
2019-08-06 15:40:17 +03:00
Aliaksandr Valialkin
f56c1298ad app/vmstorage: add vm_concurrent_addrows_* metrics for tracking concurrency for Storage.AddRows calls
Track also the number of dropped rows due to the exceeded timeout
on concurrency limit for Storage.AddRows. This number is tracked in `vm_concurrent_addrows_dropped_rows_total`
2019-08-06 15:08:43 +03:00
Aliaksandr Valialkin
a3ecf3c1f7 lib/storage: properly reset partSearch.fetchData in partSearch.reset 2019-08-05 09:55:50 +03:00
Aliaksandr Valialkin
880b1d80b1 app/vmselect: optimize /api/v1/series by skipping storage data
Fetch and process only time series metainfo.
2019-08-04 23:00:46 +03:00
Aliaksandr Valialkin
a99e89945e lib/decimal: modernize tests a bit 2019-07-31 21:09:54 +03:00
Aliaksandr Valialkin
b7c4b0c6d2 lib/storage: fix matching against tag filter with empty name
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/137
2019-07-30 15:15:21 +03:00
Aliaksandr Valialkin
c6bec48927 lib/storage: add metrics for calculating skipped rows outside the retention
The metrics are:

    - vm_too_big_timestamp_rows_total
    - vm_too_small_timestamp_rows_total
2019-07-26 14:11:56 +03:00
Aliaksandr Valialkin
f2e8d54fb0 lib/encoding/zstd: go fmt 2019-07-25 01:37:57 +03:00
Aliaksandr Valialkin
97b5dc7122 lib/encoding/zstd: disable CRC checks in pure Go build
This should give slightly better compression and decompressions performance.
Additionally this shaves off 4 bytes per each compressed block.
2019-07-24 19:17:32 +03:00
Aliaksandr Valialkin
54f035d4ce all: small updates after PR #114 2019-07-24 17:43:43 +03:00
Aliaksandr Valialkin
7a133567fb lib/encoding: small fixes in tests after the PR #114 2019-07-24 17:43:39 +03:00
Roman Khavronenko
fcf09aaa3c all: add Pure Go build (pull request #114)
Updates #94
2019-07-24 17:43:32 +03:00
Aliaksandr Valialkin
3fae34eeb4 lib/encoding: improve gauge series detection
- Series with negative values are always gauges
- Counters may only have increasing values with possible counter resets

This should improve compression ratio for gauge series which
were previously mistakenly detected as counters.
2019-07-20 14:05:25 +03:00
Aliaksandr Valialkin
7abb96b454 lib/netutil: do not count timeouts as network errors 2019-07-15 23:06:13 +03:00
Aliaksandr Valialkin
73a47d2a53 lib/storage: remove unused function isTooBigTimeRangeForDateMetricIDs 2019-07-12 02:28:40 +03:00
Aliaksandr Valialkin
97f9397687 lib/storage: do not reduce maxMetrics on time ranges exceeding maxDaysForDateMetricIDs
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/95
2019-07-12 02:21:52 +03:00
Aliaksandr Valialkin
4ca66344ee lib/storage: do not pollute inverted index with data for samples outside the retention period 2019-07-11 17:11:33 +03:00
Aliaksandr Valialkin
0522efb2d6 lib/storage: add missing tagFilter.Marshal func 2019-07-11 15:01:01 +03:00
Aliaksandr Valialkin
12b1d67b41 lib/storage: use fast path for orSuffix when searching for metricIDs against plain tag value 2019-07-11 14:48:51 +03:00
Aliaksandr Valialkin
bf2e1b0ac1 lib/storage: remember and skip individual tag filters matching too many metrics
This saves CPU time by skipping useless matching for individual tag filters.
2019-07-11 14:48:47 +03:00
Aliaksandr Valialkin
ba8195c58e all: consistency renaming: bytesSize -> sizeBytes 2019-07-10 00:47:42 +03:00
Aliaksandr Valialkin
41f512af1c all: add vm_data_size_bytes metrics for easy monitoring of on-disk data size and on-disk inverted index size 2019-07-04 19:43:04 +03:00
Aliaksandr Valialkin
6682a35731 lib/memory: attempt #3 to determine memory limit for LXC container
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/84
2019-07-01 14:01:57 +03:00
Aliaksandr Valialkin
b6ea1a7d5e lib/mergeset: make fmt 2019-06-29 14:25:46 +03:00
Aliaksandr Valialkin
ffc1bb00f6 lib/storage: skip non-matching metricIDs in sortedFilter
This should improve performance for big sorteFilter lists.
2019-06-29 13:49:40 +03:00
Aliaksandr Valialkin
2257dcd278 lib/mergeset: speed up binarySearchKey by skipping the first item during binary search 2019-06-29 13:49:32 +03:00
Aliaksandr Valialkin
6ea12a079e lib/memory: remove TestReadLXCMemoryLimit, since it doesnt work in Travis 2019-06-28 18:23:06 +03:00
Aliaksandr Valialkin
d0732d3137 lib/memory: attempt #2 to determine memory limit inside LXC container
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/84
2019-06-28 18:08:57 +03:00
Aliaksandr Valialkin
ad436757c3 lib/memory: an attempt to read proper memory limit inside LXC container
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/84
2019-06-28 15:35:02 +03:00
Aliaksandr Valialkin
416d27ef11 lib/storage: optimize time series search by regexp filter
This should improve search speed on label filters like `{foo=~"bar.+baz"}`
2019-06-27 16:18:00 +03:00
Aliaksandr Valialkin
ee23a143b9 lib/storage: make sure non-nil args are passed to openIndexDB 2019-06-25 20:10:08 +03:00
Aliaksandr Valialkin
8b0a63722f lib/storage: reduce too big maxMetrics in getTagFilterWithMinMetricIDsCountAdaptive
This should improve performance on inverted index search for big amount of unique time series
when big -search.maxUniqueTimeseries is set.
2019-06-25 19:57:31 +03:00
Aliaksandr Valialkin
0263cb0adc lib/storage: free up memory from caches owned by indexDB when it is deleted 2019-06-25 14:41:16 +03:00
Aliaksandr Valialkin
362e187011 lib/storage: use unversioned keys for tag cache in extDB
Data in ExtDB cannot be changed, so it is OK to use unversioned keys for tag cache.
This should improve performance for index lookups over big amount of time series.
2019-06-25 13:15:42 +03:00
Aliaksandr Valialkin
51e2f3b48f lib/storage: skip searching in extDB if it doesn't contain items for the given time range
This should improve inverted index search performance for big amount
of unique time series when the search is performed only on recent data.
2019-06-25 12:57:56 +03:00
Aliaksandr Valialkin
fb9358635d lib/storage: mention source parts on merge error
This should improve determining broken source part.

Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/76
2019-06-24 14:09:46 +03:00
Aliaksandr Valialkin
9164c223ec all: initial stubs for Windows support; see https://github.com/VictoriaMetrics/VictoriaMetrics/issues/70 2019-06-20 20:07:41 +03:00
Aliaksandr Valialkin
786beb8fc8 Makefile: enable golangci-lint in make check_all 2019-06-20 15:00:58 +03:00
Aliaksandr Valialkin
9cac11db64 lib/storage: typo fixes found by golangci-lint; updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/69 2019-06-20 14:38:45 +03:00
Aliaksandr Valialkin
7778030f9f lib/netutil: remove unused TCPListener.name; updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/69 2019-06-20 14:36:19 +03:00
Aliaksandr Valialkin
a0c22a6830 app/vmstorage: add vm_cache_entries{type="storage/hour_metric_ids"} metric for tracking active time series count 2019-06-19 18:37:38 +03:00
Aliaksandr Valialkin
24ae3ef532 lib/prompb: remove superflouos bytes copying in ReadSnappy 2019-06-18 21:02:02 +03:00
Aliaksandr Valialkin
e40224d5de lib/flagutil: add NewArray helper func 2019-06-18 10:44:09 +03:00
Aliaksandr Valialkin
f9e1d32168 lib/storage: persist metric ids for the current and the previous hour on graceful shutdown
This should improve performance after restart when the db contains a lot of time series
with high time series churn (i.e. metrics from Kubernetes with many pods and frequent deployments)
2019-06-14 07:55:09 +03:00
Aliaksandr Valialkin
b0b93e3d50 lib/fs: sync parent dir in MustRemoveAll only if it exists
The parent directory may be non-existing when the deleted directory
didn't exist before the MustRemoveAll call
2019-06-12 02:16:15 +03:00
Aliaksandr Valialkin
18d6f293f7 lib/fs: consolidate *RemoveAll* funcs into a single MustRemoveAll func
The func syncs parent dir in order to persist directory removal
in the event of power loss
2019-06-12 01:55:18 +03:00
Aliaksandr Valialkin
28d9904efc lib/fs: panic with fatal error when directories cannot be removed
Unremoved directories may lead to inconsistent data directory,
so VictoriaMetrics will fail to start next time.

So panic on the first error when trying to remove directory in order
to simplify recover process.
2019-06-12 01:20:10 +03:00
Aliaksandr Valialkin
d897bc3f08 lib/fs: attempt #2 to work around NFS issue with directory removal
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/61
2019-06-12 01:07:29 +03:00
Aliaksandr Valialkin
51e2e255a6 lib/fs: consistency renaming SyncPath -> MustSyncPath, since it doesnt return error 2019-06-11 23:13:45 +03:00
Aliaksandr Valialkin
3fa4c28f6b lib/fs: make sure the created directory remains visible in the fs in the event of power loss
Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/63
2019-06-11 23:08:17 +03:00
Aliaksandr Valialkin
0b7f751f60 lib/fs: use filepath.Dir instead of filepath.Split, since the filename is unused 2019-06-11 22:54:23 +03:00
Aliaksandr Valialkin
b491045a4b lib/{storage,mergeset}: sync filenames inside part when finalizing the part
Fixes https://github.com/VictoriaMetrics/VictoriaMetrics/issues/63
2019-06-11 21:51:19 +03:00
Aliaksandr Valialkin
3437c30180 all: try hard removing directory with contents
Fixes https://github.com/VictoriaMetrics/VictoriaMetrics/issues/61
2019-06-11 01:58:08 +03:00
Aliaksandr Valialkin
75a0acf72d app/vmselect: add /api/v1/labels/count handler for quick detection of labels with the maximum number of distinct values 2019-06-10 19:54:55 +03:00
Aliaksandr Valialkin
0ccedbdfd2 lib/storage: mention the accountID and projectID in error message when filtering out other (accountID, projectID) entries 2019-06-10 14:43:53 +03:00
Aliaksandr Valialkin
d54f5fec0b lib/storage: skip adaptive searching for tag filter matching the minimum number of metrics if the identical previous search didn't found such filter
This should improve speed for searching metrics among high number of time series
with high churn rate like in big Kubernetes clusters with frequent deployments.
2019-06-10 14:07:47 +03:00
Aliaksandr Valialkin
27e50e86f4 lib/storage: factor out getTagFilterWithMinMetricIDsCountAdaptive from updateMetricIDsForTagFilters 2019-06-10 13:26:00 +03:00
Aliaksandr Valialkin
b69d3dbd0c lib/storage: filter out metricIDs from another (AccountID, ProjectID) in getMetricIDsForRecentHours 2019-06-10 13:05:16 +03:00
Aliaksandr Valialkin
3059ae7be0 lib/storage: give clearer names to more functions 2019-06-10 12:59:33 +03:00
Aliaksandr Valialkin
d3a024d2d6 lib/storage: give more clear names to functions 2019-06-10 12:50:22 +03:00
Aliaksandr Valialkin
00e0760608 lib/storage: test GetSeriesCount 2019-06-10 12:40:33 +03:00
Aliaksandr Valialkin
e4cba5a7ed lib/storage: make getSeriesCount func indexSearch method 2019-06-10 12:29:24 +03:00
Aliaksandr Valialkin
d882afa905 lib/storage: optimize time series lookup for recent hours when the db contains many millions of time series with high churn rate (aka frequent deployments in Kubernetes) 2019-06-09 19:14:04 +03:00
Aliaksandr Valialkin
8cf0a0e59c app/vminsert: split vm_rows_inserted_total into per-(accountID, projectID) metrics
Fixes https://github.com/VictoriaMetrics/VictoriaMetrics/issues/59
2019-06-07 22:11:20 +03:00
Aliaksandr Valialkin
1d87abc8eb lib/procutil: typo fix in comment to WaitForSigterm 2019-06-03 16:54:37 +03:00
Aliaksandr Valialkin
a2986cde70 lib/storage: tune updating a map with today`s metric ids
- Increase update iterval from 1s to 10s. This should reduce CPU usage
  for large amounts of metric ids with constant churn.
- Reduce pendingTodayMetricIDsLock lock duration during the update.
2019-06-02 22:00:13 +03:00
Aliaksandr Valialkin
e27fd5148a lib/storage: speed up checking metricID existence in the list for the current date 2019-06-02 18:34:20 +03:00
Aliaksandr Valialkin
a6d02ff275 lib/timerpool: use timer pool in concurrency limiters
This should reduce the number of memory allocations in highly loaded system
2019-05-28 17:30:10 +03:00
Aliaksandr Valialkin
bdf696ef18 all: fix misspellings 2019-05-25 21:51:24 +03:00
Aliaksandr Valialkin
121a920a18 Makefile: add -s flag to go fmt in make fmt command 2019-05-25 21:44:36 +03:00
Aliaksandr Valialkin
9b64dfee4b lib/encoding: add vm_zstd_block_{compress|decompress}_calls_total for determining the number CompressZSTD / DecompressZSTD calls 2019-05-24 13:01:15 +03:00
Aliaksandr Valialkin
b23352dc9e lib/encoding: add vm_zstd_block_{original|compressed}_bytes_total metrics for rough estimation of block compression ratio 2019-05-24 12:34:51 +03:00
Aliaksandr Valialkin
f67f40d63a lib/encoding: substitute CompressZSTD with CompressZSTDLevel 2019-05-24 12:32:49 +03:00
Aliaksandr Valialkin
a26e774eca lib/httpserver: add -http.disableResponseCompression flag, which may help saving CPU resources at the cost of higher network bandwidth usage 2019-05-24 12:20:36 +03:00
Aliaksandr Valialkin
820cdae88d lib/decimal: add a comment explaining weird code in maxUpExponent. Fixes #29 2019-05-23 17:18:50 +03:00
Aliaksandr Valialkin
24578b4bb1 all: open-sourcing cluster version 2019-05-23 00:25:38 +03:00
Aliaksandr Valialkin
1836c415e6 all: open-sourcing single-node version 2019-05-23 00:18:06 +03:00